Li Jun, Wang Duorui, Liu Xianglong, Shi Zhiping, Wang Meng
IEEE Trans Image Process. 2022;31:341-351. doi: 10.1109/TIP.2021.3124668. Epub 2021 Dec 13.
Over the past few years, Convolutional Neural Networks (CNNs) have achieved remarkable advancement for the tasks of one-shot image classification. However, the lack of effective attention modeling has limited its performance. In this paper, we propose a Two-branch (Content-aware and Position-aware) Attention (CPA) Network via an Efficient Semantic Coupling module for attention modeling. Specifically, we harness content-aware attention to model the characteristic features (e.g., color, shape, texture) as well as position-aware attention to model the spatial position weights. In addition, we exploit support images to improve the learning of attention for the query images. Similarly, we also use query images to enhance the attention model of the support set. Furthermore, we design a local-global optimizing framework that further improves the recognition accuracy. The extensive experiments on four common datasets (miniImageNet, tieredImageNet, CUB-200-2011, CIFAR-FS) with three popular networks (DPGN, RelationNet and IFSL) demonstrate that our devised CPA module equipped with local-global Two-stream framework (CPAT) can achieve state-of-the-art performance, with a significant improvement in accuracy of 3.16% on CUB-200-2011 in particular.
在过去几年中，卷积神经网络（CNN）在一次性图像分类任务上取得了显著进展。然而，缺乏有效的注意力建模限制了其性能。在本文中，我们通过一个高效语义耦合模块提出了一种双分支（内容感知和位置感知）注意力（CPA）网络用于注意力建模。具体来说，我们利用内容感知注意力来对特征（如颜色、形状、纹理）进行建模，以及利用位置感知注意力来对空间位置权重进行建模。此外，我们利用支撑图像来改进查询图像的注意力学习。同样，我们也使用查询图像来增强支撑集的注意力模型。此外，我们设计了一个局部-全局优化框架，进一步提高识别准确率。在四个常见数据集（miniImageNet、tieredImageNet、CUB-200-2011、CIFAR-FS）上使用三个流行网络（DPGN、RelationNet和IFSL）进行的广泛实验表明，我们设计的配备局部-全局双流框架（CPAT）的CPA模块能够实现当前最优性能，特别是在CUB-200-2011上准确率有显著提高3.16%。
